Thermogram analysis and classification in breast cancer diagnostics

Thermography based breast cancer analysis using statistical features and fuzzy classification

“…However it should be noted that a correct classification rate of 80% is comparable to that achieved by other techniques for breast cancer diagnosis with mammography typically providing about 80%, ultrasonography about 70%, MRI systems about 75% and DOBI (optical systems) reaching about 80% diagnostic accuracy [18]. We can therefore conclude that our presented approach is indeed useful as an aid for diagnosis of breast cancer and should prove even more powerful when coupled with another modality such as mammography.…”

Breast Cancer Classification Using Statistical Features and Fuzzy Classification of Thermograms

“…That there is a fairly significant drop in terms of classification performance once again confirms the difficulty of the dataset. However it should be noted that a correct classification rate of 80% is comparable to that [17]. We can therefore conclude that our presented approach provides indeed useful for the automatic diagnosis of breast cancer and should prove even more powerful when coupled with another modality such as mammography.…”

Intelligent Rule-based Classification of Image Features for Breast Thermogram Analysis

“…This is the same dataset that was used in Ref. 11 and is significantly larger than those used in other studies (e.g. Ref.…”

“…Using this configuration, a classification accuracy of 80.89% was achieved, which is similar to that obtained by other imaging modalities. 11 …”

“…In order to arrive at an indication of asymmetry between the two sides, we use the cross co-occurrence matrix 11 where one pixel value is extracted from the left breast and the other from the right. From this matrix, we extract some statistical features, namely homogeneity, energy, contrast, and symmetry, 10 and the first four moments of the matrix.…”